Skip to content

lim-asdk/arsenal-Workspace_v1

Repository files navigation

Lim Workspace

Lim Workspace is a developer-first AI + MCP workspace skeleton. It is designed to help you wire local profiles, local MCP servers, and a shared desktop/browser UI into one public starter repo.

What This Repo Is

  • a runnable desktop and browser workspace skeleton
  • a local-first AI profile and MCP server setup surface
  • a public launcher hub for GitHub visitors
  • a clean base for adding your own providers, servers, and workflows

Public Launchers

The canonical GitHub-friendly launchers live in ui_launchers/:

The older run_*.cmd wrappers remain only for compatibility. New users and contributors should start from the ui_ launchers.

Repository Layout

  • apps/desktop: desktop app entry layer
  • apps/server: browser/server entry layer
  • packages/desktop_ui: shared product UI
  • packages/agent_runtime: AI orchestration runtime
  • packages/mcp_gateway: MCP connection and tool registry layer
  • packages/settings_service: profile, secrets, and local config handling
  • servers: bundled MCP servers for the first product slice
  • config/profiles: public AI profile templates
  • config/mcp: public MCP server templates
  • ui_launchers: public launcher entry points
  • docs: public-facing docs for GitHub and search discoverability
  • docs_internal: local-only internal notes, excluded from Git
  • user_data: runtime-generated local data, excluded from Git

Public Positioning

  • this repo is intended as a starter skeleton, not a polished end-user product
  • public docs should help developers understand setup, extension points, and validation quickly
  • general-user instructions should stay short and practical
  • internal planning and implementation notes stay in docs_internal

Secret Policy

  • real secrets must never be committed
  • GitHub should contain .env.example, not .env
  • non-secret AI and MCP settings belong in readable JSON files
  • user-specific runtime files belong under user_data/
  • local desktop testing may keep provider keys in user_data/profiles/*.json
  • public template files must stay secret-free

Config Strategy

  • .env: optional secret values and overrides
  • config/profiles/*.json: public AI profile templates
  • config/mcp/*.json: public MCP server templates
  • user_data/profiles/*.json: local runtime AI profiles
  • user_data/mcp/*.json: local runtime MCP configs
  • browser/server mode defaults to 127.0.0.1:38761
  • JSON should stay simple enough for developers to copy, edit, and extend

Docs

Public Release Standards

  • public release guidance should be easy to find from the repository root
  • standard GitHub trust documents should exist for security, contribution, and release history
  • the repository root should include SECURITY.md, CONTRIBUTING.md, and CHANGELOG.md
  • public-facing docs should stay safe for publication and avoid private business context
  • screenshots, logs, and sample JSON should stay secret-free

Current Status

The current workspace slice is wired up with:

  • one working xAI Grok profile path
  • one bundled global_finance MCP server path
  • a setup-focused UI shared by desktop and browser launchers
  • AI connection test, MCP connection test, manual tool test, and chat workflow

Validation

The workspace is currently validated through:

  • desktop launcher startup
  • browser mode launcher startup on 127.0.0.1:38761
  • HTTP server startup and /api/health checks
  • smoke tests in tests/
  • real MCP tool discovery and chat flow validation

The next implementation phase should harden:

  • broader onboarding
  • safer connection permissions
  • additional provider/server templates
  • packaging and installer flow

About

Developer-first AI + MCP workspace skeleton

Topics

Resources

License

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Contributors